Autonomous Vehicle Lane Mapping for Motorcycle And Trailer Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating around motorcycles and groups of motorcycles, particularly in situations where lane splitting is permitted or not, and in handling trailers and stationary vehicles on roadways, while adhering to local regulations and avoiding collisions.
Innovation Solution
The system employs sensors like LiDAR, cameras, and radar to detect motorcycles and trailers, classifies their behavior, determines navigation parameters, and adjusts trajectories to avoid collisions and comply with lane-splitting regulations, while also predicting trailer trajectories and avoiding stationary vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous vehicle maintains a standard trajectory in adjacent lanes, then navigation efficiency is improved, but collision risk with lane-splitting motorcycles increases
Solution Approach 1:
The system dynamically adjusts the trajectory based on real-time detection of motorcycle behavior states. When lane splitting is detected, the trajectory is modified to avoid the motorcycle; when not detected, the standard efficient trajectory is maintained. This dynamic adaptation resolves the contradiction between navigation efficiency and collision risk.
Solution Approach 2:
The behavior state classification system acts as an intermediary between raw sensor data and trajectory planning. It processes motorcycle detection data to determine whether lane splitting is occurring, then uses this classification to adjust the trajectory parameter, serving as a mediator that enables safe navigation without sacrificing efficiency.
2Reliability
If the autonomous vehicle restricts trajectory into adjacent lanes, then safety around motorcycles is improved, but navigation flexibility deteriorates
Solution Approach 1:
The lane permission parameter is dynamically set based on motorcycle behavior state classification. When motorcycles are detected in lane-splitting behavior, the parameter restricts trajectory into adjacent lanes; when not detected, the parameter allows flexible navigation. This dynamic adjustment maintains both safety and flexibility.
3Measurement precision
If the autonomous vehicle uses complex sensor processing to classify motorcycle behavior, then detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The system segments motorcycle detection into distinct behavior state categories (lane splitting vs. not lane splitting) based on spatial position relative to the autonomous vehicle. This segmentation simplifies the classification task while maintaining detection accuracy, as each category has clear geometric criteria rather than requiring complex analysis.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables safe and lawful operation of autonomous vehicles by dynamically adjusting navigation to account for motorcycles, trailers, and stationary vehicles, ensuring compliance with local laws and minimizing risks.
Implementation Method 1
detecting, via sensor data collected from sensors located on the autonomous vehicle
Implementation Method 2
The system employs sensors like LiDAR, cameras, and radar to detect motorcycles and trailers
Data Source
AI summary
An example method includes detecting, via sensor data collected from sensors located on the AV, an upcoming object located on a roadway. The method further includes determining, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle. The method further includes mapping the upcoming object to an absolute location with respect to the roadway based on map data that describes upcoming topology of the roadway and a location of the autonomous vehicle. The method further includes associating the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway. The method further includes operating the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located.